import pandas as pd

# Load the downloaded CSV file
data = pd.read_csv('knn_authentication_features.csv')
print("Loaded Data:")
data.head()

Loaded Data:

list(data.columns)

['filename',
 'label',
 'student_id',
 'Mfcc_1',
 'Mfcc_2',
 'Mfcc_3',
 'Mfcc_4',
 'Mfcc_5',
 'Mfcc_6',
 'Mfcc_7',
 'Mfcc_8',
 'Mfcc_9',
 'Mfcc_10',
 'Mfcc_11',
 'Mfcc_12',
 'Mfcc_13',
 'Spectral_Contrast_1',
 'Spectral_Contrast_2',
 'Spectral_Contrast_3',
 'Spectral_Contrast_4',
 'Spectral_Contrast_5',
 'Spectral_Contrast_6',
 'Spectral_Contrast_7',
 'Zero_Crossing_Rate',
 'RMS_Energy',
 'Spectral_Centroid',
 'Spectral_Bandwidth']

data['RMS_Energy'] = data['RMS_Energy'].astype(str).str.replace('[', '', regex=False).str.replace(']', '', regex=False).astype(float)

import numpy as np
import pandas as pd
from sklearn.model_selection import KFold
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import accuracy_score, confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt

def k_fold_cross_validation(df, feature_names, target_name, model, feature_reduction_func, k=5):
    """
    Perform k-fold cross-validation on the given data.

    Parameters:
    df (pd.DataFrame): The input data frame.
    feature_names (list): List of feature column names.
    target_name (str): The name of the target column.
    model: The classification model to be used.
    feature_reduction_func: The feature reduction function to be applied.
    k (int): The number of folds for cross-validation (default is 5).

    Returns:
    float: The average accuracy score across all folds.
    """
    X = df[feature_names]
    y = df[target_name]

    kf = KFold(n_splits=k, shuffle=True, random_state=42)
    accuracies = []
    confusion_matrices = []

    for train_index, test_index in kf.split(X):
        X_train, X_test = X.iloc[train_index], X.iloc[test_index]
        y_train, y_test = y.iloc[train_index], y.iloc[test_index]

        # Feature scaling
        scaler = StandardScaler()
        X_train_scaled = scaler.fit_transform(X_train)
        X_test_scaled = scaler.transform(X_test)

        # Feature reduction
        if(feature_reduction_func):
          X_train_scaled = feature_reduction_func.fit_transform(X_train_scaled, y_train)
          X_test_scaled = feature_reduction_func.transform(X_test_scaled)


        model.fit(X_train_scaled, y_train)

        # Make predictions

        #test_accuracy = model.evaluate(X_test_scaled, y_test)
        y_pred = model.predict(X_test_scaled)

        # Calculate accuracy
        accuracy = accuracy_score(y_test, y_pred)
        accuracies.append(accuracy)

        # Generate confusion matrix
        conf_matrix = confusion_matrix(y_test, y_pred)
        confusion_matrices.append(conf_matrix)

    # Calculate average accuracy
    avg_accuracy = np.mean(accuracies)*100
    std_accuracy = np.std(accuracies)*100

    # Plot the average confusion matrix
    avg_conf_matrix = np.mean(confusion_matrices, axis=0)
    plt.figure(figsize=(5, 3))
    sns.heatmap(avg_conf_matrix, annot=True, fmt='.2f', cmap='Blues')
    plt.xlabel('Predicted')
    plt.ylabel('Actual')
    plt.title('Average Confusion Matrix')
    plt.show()

    return avg_accuracy, std_accuracy

def Plot_Results_Barchart(results_df):

  # List of feature reduction methods
  feature_reductions = results_df['Feature Reduction'].unique()

  # Set a pleasing color palette
  sns.set_palette("Set2")

  # Loop to plot bar charts for each feature reduction method
  for reduction in feature_reductions:
      # Filter data for the current feature reduction method
      filtered_results = results_df[results_df['Feature Reduction'] == reduction]
      max_value = filtered_results['Mean Accuracy'].max()
      print(f"Maximum accuracy if feature reduction({reduction}): {max_value:.2f}%")

      # Plot the bar chart
      plt.figure(figsize=(7, 5))
      ax = sns.barplot(x='Feature Set', y='Mean Accuracy', hue='Model', data=filtered_results, errorbar=None, width=0.4)


      # Add solid lines around each bar
      for bar in ax.patches:
          if bar.get_height() == max_value:
              bar.set_edgecolor('red')
              bar.set_linewidth(2)
          else:
              bar.set_edgecolor('black')
              bar.set_linewidth(0.5)

      # Set titles and labels
      plt.title(f'Cross-Validation Mean Accuracy for Different Models ({reduction})', fontsize=10)
      plt.xlabel('Feature Set', fontsize=8)
      plt.ylabel('Mean Accuracy', fontsize=8)
      plt.ylim(0, 100)
      plt.xticks(fontsize=8)
      plt.yticks(fontsize=8)
      plt.legend(title='Model', loc='upper center', bbox_to_anchor=(0.5, -0.2), ncol=3, fontsize=8)

      plt.tight_layout()
      plt.show()

from sklearn.neighbors import KNeighborsClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC


from sklearn.decomposition import PCA
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

def Run_Classification(balanced_dataFrame):
  # Define the feature sets
  mfcc_features = [f'Mfcc_{i+1}' for i in range(13)]
  spectral_contrast_features = [f'Spectral_Contrast_{i+1}' for i in range(7)]
  combined_features = mfcc_features + spectral_contrast_features
  time_features = ['Zero_Crossing_Rate',	'RMS_Energy']
  Spec_cent_Bw = ['Spectral_Centroid',	'Spectral_Bandwidth']
  all_features = combined_features + time_features + Spec_cent_Bw

  balanced_dataFrame['RMS_Energy'] = balanced_dataFrame['RMS_Energy'].astype(str).str.replace('[', '', regex=False).str.replace(']', '', regex=False).astype(float)

  # Define the target column
  target_column = 'class'

  # Define the models
  models = {
      'KNN': KNeighborsClassifier(n_neighbors=5),
      'Logistic Regression': LogisticRegression( max_iter=200, random_state= 42),
      'SVM': SVC(kernel='linear', random_state=42)
  }

  # Define the feature sets
  feature_sets = {
      'time_domain_features' : time_features,
      'MFCC': mfcc_features,
      'Spectral Contrast': spectral_contrast_features,
      'MFCC&Sp_Contrast': combined_features,
      'Spec_Cent&BW': Spec_cent_Bw,
      'all_features' : all_features
  }

  feature_reductions = {
      'LDA': LinearDiscriminantAnalysis(),
      'PCA': PCA(),
      'None': None
  }

  # Run cross-validation and store results
  results = []
  for model_name, model in models.items():
      for feature_set_name, feature_columns in feature_sets.items():
          for reduction_name, reduction_func in feature_reductions.items():
              print(f'\nModel({model_name}) using feature({feature_set_name}) and feature reduction({reduction_name})\n')
              mean_accuracy, std_accuracy = k_fold_cross_validation(balanced_dataFrame, feature_columns, target_column, model, reduction_func, k=4)
              results.append({
                  'Model': model_name,
                  'Feature Set': feature_set_name,
                  'Feature Reduction': reduction_name,
                  'Mean Accuracy': mean_accuracy,
                  'Std Accuracy': std_accuracy
                  })

  results_df = pd.DataFrame(results)
  return results_df

import random

random.seed(42)

# Get unique student IDs
student_ids = data['student_id'].unique()

# Randomly select 6 students
selected_students = random.sample(list(student_ids), 6)
print(f"Selected Students: {selected_students}")

Selected Students: [np.int64(810103183), np.int64(810100091), np.int64(810198554), np.int64(810103317), np.int64(810199489), np.int64(810101465)]

from sklearn.utils import shuffle

filtered_data = data[data['student_id'].isin(selected_students)]

# Ensure each student has an equal number of samples
balanced_data = filtered_data.groupby('student_id').apply(lambda x: x.sample(n=filtered_data['student_id'].value_counts().min(), random_state=42)).reset_index(drop=True)
balanced_data = shuffle(balanced_data, random_state=42)
balanced_data.reset_index(drop=True, inplace=True)

print("Number of samples for each student in the balanced DataFrame:")
print(balanced_data['student_id'].value_counts())

Number of samples for each student in the balanced DataFrame:
student_id
810103183    123
810101465    123
810198554    123
810199489    123
810103317    123
810100091    123
Name: count, dtype: int64

/tmp/ipykernel_15412/3536119780.py:6: DeprecationWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.
  balanced_data = filtered_data.groupby('student_id').apply(lambda x: x.sample(n=filtered_data['student_id'].value_counts().min(), random_state=42)).reset_index(drop=True)

import seaborn as sns


mfcc_features = [f'Mfcc_{i+1}' for i in range(13)]
# Plot pair plot
palette = sns.color_palette("tab10", balanced_data['student_id'].nunique())
sns.pairplot(balanced_data, hue='student_id', vars= mfcc_features, palette=palette)

# Display the plot
plt.show()

import seaborn as sns

spectral_contrast_features = [f'Spectral_Contrast_{i+1}' for i in range(7)]
# Plot pair plot
palette = sns.color_palette("tab10", balanced_data['student_id'].nunique())
sns.pairplot(balanced_data, hue='student_id', vars= spectral_contrast_features, palette=palette)

# Display the plot
plt.show()

import seaborn as sns

time_features = ['Zero_Crossing_Rate',	'RMS_Energy']
# Plot pair plot
palette = sns.color_palette("tab10", balanced_data['student_id'].nunique())
sns.pairplot(balanced_data, hue='student_id', vars= time_features, palette=palette)

# Display the plot
plt.show()

# Map student IDs to class labels (e.g., 0 to 5)
class_mapping = {student_id: idx for idx, student_id in enumerate(selected_students)}
balanced_data['class'] = balanced_data['student_id'].map(class_mapping)


print("Balanced DataFrame with Class Column:")
balanced_data.tail()

Balanced DataFrame with Class Column:

Result_DF = Run_Classification(balanced_data)

Model(KNN) using feature(time_domain_features) and feature reduction(LDA)

Model(KNN) using feature(time_domain_features) and feature reduction(PCA)

Model(KNN) using feature(time_domain_features) and feature reduction(None)

Model(KNN) using feature(MFCC) and feature reduction(LDA)

Model(KNN) using feature(MFCC) and feature reduction(PCA)

Model(KNN) using feature(MFCC) and feature reduction(None)

Model(KNN) using feature(Spectral Contrast) and feature reduction(LDA)

Model(KNN) using feature(Spectral Contrast) and feature reduction(PCA)

Model(KNN) using feature(Spectral Contrast) and feature reduction(None)

Model(KNN) using feature(MFCC&Sp_Contrast) and feature reduction(LDA)

df_sorted = Result_DF.sort_values(by='Mean Accuracy', ascending=False)
df_sorted.head()

Plot_Results_Barchart(Result_DF)

Maximum accuracy if feature reduction(LDA): 99.73%

Maximum accuracy if feature reduction(PCA): 99.46%

Maximum accuracy if feature reduction(None): 99.46%

import random

random.seed(8)

# Get unique student IDs
student_ids = data['student_id'].unique()

# Randomly select 6 students
selected_students = random.sample(list(student_ids), 6)
print(f"Selected Students: {selected_students}")

Selected Students: [np.int64(810102148), np.int64(810100193), np.int64(810600133), np.int64(810103054), np.int64(810100206), np.int64(810100168)]

from sklearn.utils import shuffle

filtered_data = data[data['student_id'].isin(selected_students)]

# Ensure each student has an equal number of samples
balanced_data = filtered_data.groupby('student_id').apply(lambda x: x.sample(n=filtered_data['student_id'].value_counts().min(), random_state=42)).reset_index(drop=True)
balanced_data = shuffle(balanced_data, random_state=42)
balanced_data.reset_index(drop=True, inplace=True)

print("Number of samples for each student in the balanced DataFrame:")
print(balanced_data['student_id'].value_counts())

Number of samples for each student in the balanced DataFrame:
student_id
810600133    97
810100206    97
810100193    97
810103054    97
810102148    97
810100168    97
Name: count, dtype: int64

/tmp/ipykernel_15412/3536119780.py:6: DeprecationWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.
  balanced_data = filtered_data.groupby('student_id').apply(lambda x: x.sample(n=filtered_data['student_id'].value_counts().min(), random_state=42)).reset_index(drop=True)

# Map student IDs to class labels (e.g., 0 to 5)
class_mapping = {student_id: idx for idx, student_id in enumerate(selected_students)}
balanced_data['class'] = balanced_data['student_id'].map(class_mapping)

print("Balanced DataFrame with Class Column:")
balanced_data.tail()

Balanced DataFrame with Class Column:

Result_DF = Run_Classification(balanced_data)

Model(KNN) using feature(time_domain_features) and feature reduction(LDA)

Model(KNN) using feature(time_domain_features) and feature reduction(PCA)

Model(KNN) using feature(time_domain_features) and feature reduction(None)

Model(KNN) using feature(MFCC) and feature reduction(LDA)

Model(KNN) using feature(MFCC) and feature reduction(PCA)

Model(KNN) using feature(MFCC) and feature reduction(None)

Model(KNN) using feature(Spectral Contrast) and feature reduction(LDA)

Model(KNN) using feature(Spectral Contrast) and feature reduction(PCA)

Model(KNN) using feature(Spectral Contrast) and feature reduction(None)

Model(KNN) using feature(MFCC&Sp_Contrast) and feature reduction(LDA)

df_sorted = Result_DF.sort_values(by='Mean Accuracy', ascending=False)
df_sorted.head()

Plot_Results_Barchart(Result_DF)

Maximum accuracy if feature reduction(LDA): 98.97%

Maximum accuracy if feature reduction(PCA): 99.66%

Maximum accuracy if feature reduction(None): 99.66%

import random

random.seed(1403)

# Get unique student IDs
student_ids = data['student_id'].unique()

# Randomly select 6 students
selected_students = random.sample(list(student_ids), 6)
print(f"Selected Students: {selected_students}")

Selected Students: [np.int64(810101401), np.int64(610300070), np.int64(810103054), np.int64(810100261), np.int64(810103317), np.int64(810101456)]

from sklearn.utils import shuffle

filtered_data = data[data['student_id'].isin(selected_students)]

# Ensure each student has an equal number of samples
balanced_data = filtered_data.groupby('student_id').apply(lambda x: x.sample(n=filtered_data['student_id'].value_counts().min(), random_state=42)).reset_index(drop=True)
balanced_data = shuffle(balanced_data, random_state=42)
balanced_data.reset_index(drop=True, inplace=True)

print("Number of samples for each student in the balanced DataFrame:")
print(balanced_data['student_id'].value_counts())

Number of samples for each student in the balanced DataFrame:
student_id
810103054    139
810103317    139
810101401    139
810100261    139
610300070    139
810101456    139
Name: count, dtype: int64

/tmp/ipykernel_15412/3536119780.py:6: DeprecationWarning: DataFrameGroupBy.apply operated on the grouping columns. This behavior is deprecated, and in a future version of pandas the grouping columns will be excluded from the operation. Either pass `include_groups=False` to exclude the groupings or explicitly select the grouping columns after groupby to silence this warning.
  balanced_data = filtered_data.groupby('student_id').apply(lambda x: x.sample(n=filtered_data['student_id'].value_counts().min(), random_state=42)).reset_index(drop=True)

# Map student IDs to class labels (e.g., 0 to 5)
class_mapping = {student_id: idx for idx, student_id in enumerate(selected_students)}
balanced_data['class'] = balanced_data['student_id'].map(class_mapping)

print("Balanced DataFrame with Class Column:")
balanced_data.tail()

Balanced DataFrame with Class Column:

Result_DF = Run_Classification(balanced_data)

Model(KNN) using feature(time_domain_features) and feature reduction(LDA)

Model(KNN) using feature(time_domain_features) and feature reduction(PCA)

Model(KNN) using feature(time_domain_features) and feature reduction(None)

Model(KNN) using feature(MFCC) and feature reduction(LDA)

Model(KNN) using feature(MFCC) and feature reduction(PCA)

Model(KNN) using feature(MFCC) and feature reduction(None)

Model(KNN) using feature(Spectral Contrast) and feature reduction(LDA)

Model(KNN) using feature(Spectral Contrast) and feature reduction(PCA)

Model(KNN) using feature(Spectral Contrast) and feature reduction(None)

Model(KNN) using feature(MFCC&Sp_Contrast) and feature reduction(LDA)

df_sorted = Result_DF.sort_values(by='Mean Accuracy', ascending=False)
df_sorted.head()

Plot_Results_Barchart(Result_DF)

Maximum accuracy if feature reduction(LDA): 99.88%

Maximum accuracy if feature reduction(PCA): 99.88%

Maximum accuracy if feature reduction(None): 99.88%

	filename	label	student_id	Mfcc_1	Mfcc_2	Mfcc_3	Mfcc_4	Mfcc_5	Mfcc_6	Mfcc_7	...	Spectral_Contrast_2	Spectral_Contrast_3	Spectral_Contrast_4	Spectral_Contrast_5	Spectral_Contrast_6	Spectral_Contrast_7	Zero_Crossing_Rate	RMS_Energy	Spectral_Centroid	Spectral_Bandwidth
0	hw1_q2_610399205_male.mp3_0	male	610399205	-94.829977	122.175083	-68.000374	47.507958	-14.407363	-13.427573	-23.064053	...	16.537672	17.337876	15.638074	18.102693	23.265461	66.736837	0.105971	[0.24632083]	1911.823347	1581.462113
1	hw1_q2_610399205_male.mp3_1	male	610399205	-123.197408	131.659141	-61.479495	44.792372	-7.927916	-10.119547	-21.518692	...	16.173748	17.615650	15.370934	17.944107	21.722387	64.664952	0.079931	[0.21608743]	1656.721908	1499.382229
2	hw1_q2_610399205_male.mp3_2	male	610399205	-122.910702	141.014834	-67.712628	39.928565	-14.785694	-7.251495	-24.902940	...	15.759529	17.226226	15.636203	18.222485	21.671965	63.307834	0.096313	[0.19001988]	1707.593297	1448.149975
3	hw1_q2_610399205_male.mp3_3	male	610399205	-140.025639	126.584783	-53.874062	40.963797	-5.784167	-5.752144	-22.515332	...	15.341300	15.522699	14.462609	18.687998	22.817218	61.284887	0.099141	[0.16602059]	1857.183068	1591.809683
4	hw1_q2_610399205_male.mp3_4	male	610399205	-127.307332	122.204455	-61.316071	54.882303	-0.544779	-11.455723	-28.317545	...	17.254408	17.243651	14.808253	19.110663	23.740752	67.221951	0.096767	[0.21153131]	1830.105791	1537.769633

	filename	label	student_id	Mfcc_1	Mfcc_2	Mfcc_3	Mfcc_4	Mfcc_5	Mfcc_6	Mfcc_7	...	Spectral_Contrast_3	Spectral_Contrast_4	Spectral_Contrast_5	Spectral_Contrast_6	Spectral_Contrast_7	Zero_Crossing_Rate	RMS_Energy	Spectral_Centroid	Spectral_Bandwidth	class
733	hw1_q1_810100091_male.mp3_14	male	810100091	-209.270224	159.299467	-12.862626	38.995735	-8.071367	1.210875	-26.295211	...	18.579838	16.371176	18.578580	18.729660	57.705217	0.045901	0.146539	1065.860536	1343.465670	1
734	hw1_q4_810100091_male.mp3_35	male	810100091	-180.091125	158.623054	-8.343020	38.221878	0.616179	6.856343	-26.354627	...	17.178651	14.908284	17.176830	17.841851	58.990186	0.047214	0.206644	1160.097436	1424.149759	1
735	hw1_q4_810103183_male.mp3_2	male	810103183	-197.288841	153.435223	-21.336439	39.097099	-28.892864	-4.788617	-17.154573	...	18.552319	16.887290	18.161144	22.510156	58.677515	0.074786	0.160438	1388.911960	1346.191071	0
736	hw1_q4_810103317_male.mp3_27	male	810103317	-196.783701	156.871713	2.812224	30.233925	4.374440	-1.058855	-26.090089	...	20.248830	16.543377	19.366785	18.958355	58.715747	0.054211	0.242592	1063.924159	1260.229348	3
737	hw1_q1_810100091_male.mp3_9	male	810100091	-161.626642	153.208495	-11.947535	47.287845	-4.489833	-2.877725	-31.232691	...	19.821527	17.225590	17.476504	18.599111	60.334727	0.049144	0.271515	1141.883666	1375.061913	1

	filename	label	student_id	Mfcc_1	Mfcc_2	Mfcc_3	Mfcc_4	Mfcc_5	Mfcc_6	Mfcc_7	...	Spectral_Contrast_3	Spectral_Contrast_4	Spectral_Contrast_5	Spectral_Contrast_6	Spectral_Contrast_7	Zero_Crossing_Rate	RMS_Energy	Spectral_Centroid	Spectral_Bandwidth	class
577	hw1_q6_810100168_female.mp3_56	female	810100168	-211.851905	132.622349	-26.187861	7.499521	-15.446996	-16.373846	-20.007774	...	18.901962	18.813562	19.578638	19.716234	57.092843	0.086897	0.141222	1430.544644	1292.170410	5
578	hw1_q2_810100193_female.mp3_9	female	810100193	-184.267192	124.399497	5.529370	41.731653	-26.419279	-8.033805	-17.266343	...	15.281587	16.121414	16.699920	16.846284	65.358917	0.055890	0.229206	1321.779222	1616.504355	1
579	hw1_q6_810100206_male.mp3_78	male	810100206	-264.700924	180.204484	16.873536	30.587170	-10.826312	-5.214259	-29.595162	...	18.114748	16.465813	17.164280	16.028635	51.030329	0.051165	0.117173	893.509100	1109.506454	4
580	hw1_q6_810103054_male.mp3_22	male	810103054	-223.577594	137.644504	-7.995220	38.862804	-18.405657	14.722776	-18.204598	...	19.636023	14.571491	18.150354	18.250443	59.959546	0.041126	0.132037	1133.692981	1511.824107	3
581	hw1_q3_810100193_female.mp3_17	female	810100193	-177.964937	146.832626	2.405349	40.226782	-23.222275	-23.508371	-36.809802	...	19.449307	18.994886	17.612312	17.172073	59.866017	0.049638	0.214573	1117.108282	1373.884490	1

	filename	label	student_id	Mfcc_1	Mfcc_2	Mfcc_3	Mfcc_4	Mfcc_5	Mfcc_6	Mfcc_7	...	Spectral_Contrast_3	Spectral_Contrast_4	Spectral_Contrast_5	Spectral_Contrast_6	Spectral_Contrast_7	Zero_Crossing_Rate	RMS_Energy	Spectral_Centroid	Spectral_Bandwidth	class
829	hw1_q1_610300070_female.mp3_78	female	610300070	-175.235198	102.698340	-29.725138	42.060783	-30.536303	-2.644054	-35.779279	...	22.399559	18.455236	19.463346	21.840109	63.809065	0.081916	0.253871	1622.742829	1600.531925	1
830	hw1_q5_610300070_female.mp3_3	female	610300070	-228.418644	113.546638	-1.372091	31.949328	-20.382214	-5.201409	-15.191473	...	20.273068	16.249352	17.684594	22.089427	63.913752	0.061365	0.159174	1363.107072	1594.767166	1
831	hw1_q1_810100261_male.mp3.mp3_1	male	810100261	-210.533109	107.467373	-34.426835	39.903486	1.809619	-4.967549	-22.326968	...	21.508174	19.111921	21.422158	26.465331	62.774750	0.108192	0.148817	1925.854474	1603.347033	3
832	hw1_q1_810101456_female.mp3_98	female	810101456	-202.050703	95.903137	-48.087167	19.064818	-20.076070	-17.911852	-34.061431	...	24.042378	20.284681	22.179613	20.614573	65.130201	0.077171	0.185471	1654.069415	1611.754747	5
833	hw1_q1_610300070_female.mp3_18	female	610300070	-223.128404	105.228311	-8.214977	41.257315	-31.044399	4.772623	-33.162689	...	20.590256	16.414522	19.069961	19.842611	62.274789	0.078410	0.159881	1593.538096	1701.605259	1

Load the dataset from a CSV file and Create DataFrame¶

Utills¶

K_fold_Crossvalidation Function:¶

Visualization of Cross-Validation Results¶

Plot_Results_Barchart¶

Classification Using Different Models, Feature Reduction, and Feature Sets¶

Run_Classification¶

Random Student Set1¶

Pairplot Visualization:¶

Classification and Analysis for Student Set1¶

Classification Process and Average Confusion Matrix¶

Calling the Classification Function¶

Sorting and Displaying Top Results¶

Ploting Results¶

Random Student Set2¶

Classification and Analysis for Student Set2¶

Classification Process and Average Confusion Matrix¶

Calling the Classification Function¶

Sorting and displaying Top Results¶

Ploting Results¶

Random Student Set3¶

Classification and Analysis for Student Set3¶

Classification Process and Average Confusion Matrix¶

Calling the Classification Function¶

Sorting and displaying Top Results¶

Ploting Results¶

	Model	Feature Set	Feature Reduction	Mean Accuracy	Std Accuracy
15	KNN	all_features	LDA	99.729730	0.468122
34	Logistic Regression	all_features	PCA	99.459459	0.540541
51	SVM	all_features	LDA	99.459459	0.540541
33	Logistic Regression	all_features	LDA	99.459459	0.540541
35	Logistic Regression	all_features	None	99.459459	0.540541

	Model	Feature Set	Feature Reduction	Mean Accuracy	Std Accuracy
47	SVM	MFCC&Sp_Contrast	None	99.655172	0.344828
46	SVM	MFCC&Sp_Contrast	PCA	99.655172	0.344828
53	SVM	all_features	None	99.485120	0.297272
52	SVM	all_features	PCA	99.485120	0.297272
10	KNN	MFCC&Sp_Contrast	PCA	99.312707	0.002362

	Model	Feature Set	Feature Reduction	Mean Accuracy	Std Accuracy
9	KNN	MFCC&Sp_Contrast	LDA	99.880383	0.207183
51	SVM	all_features	LDA	99.880383	0.207183
33	Logistic Regression	all_features	LDA	99.880383	0.207183
34	Logistic Regression	all_features	PCA	99.880383	0.207183
35	Logistic Regression	all_features	None	99.880383	0.207183